AI RESEARCH
S-MARC: Causal Streaming Reasoning for Full-Duplex Conversational Behavior Modeling
arXiv CS.AI
•
ArXi:2602.11065v2 Announce Type: replace-cross Human conversation is organized by an implicit chain of thought and manifests as temporally structured conversational behaviors. Capturing this perceptual pathway is critical for building natural full-duplex interactive systems. We propose S-MARC (Streaming Causal Modeling and Reasoning for Conversation), a streaming, causal, and hierarchical framework for conversational behavior modeling and reasoning.